BriefGPT.xyz
Apr, 2018
使用百万像素图像训练卷积神经网络
Training convolutional neural networks with megapixel images
HTML
PDF
Hans Pinckaers, Geert Litjens
TL;DR
本文介绍了一种可以在有限的内存下训练深度卷积神经网络的方法，可以使用较大的图像尺寸，并通过定量比较证明了该方法与传统方法等效。
Abstract
To train
deep convolutional neural networks
, the input data and the intermediate activations need to be kept in memory to calculate the
gradient descent
step. Given the
→